Skip to content

Bugfix for flux2 img2img2 prediction #12855

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
leisuzz wants to merge 5 commits into
base: main
Choose a base branch
from
+9 −2
Open

Bugfix for flux2 img2img2 prediction #12855

Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
e1cf6a3
Bugfix for dreambooth flux2 img2img2
leisuzz Dec 18, 2025
e3556db
Bugfix for dreambooth flux2 img2img2
leisuzz Dec 18, 2025
79f704c
Bugfix for dreambooth flux2 img2img2
leisuzz Dec 18, 2025
e5229da
Bugfix for dreambooth flux2 img2img2
leisuzz Dec 18, 2025
86da067
Bugfix for dreambooth flux2 img2img2
leisuzz Dec 18, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 9 additions & 2 deletions examples/dreambooth/train_dreambooth_lora_flux2_img2img.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1621,9 +1621,13 @@ def get_sigmas(timesteps, n_dim=4, dtype=torch.float32):
cond_model_input = (cond_model_input - latents_bn_mean) / latents_bn_std

model_input_ids = Flux2Pipeline._prepare_latent_ids(model_input).to(device=model_input.device)
cond_model_input_ids = Flux2Pipeline._prepare_image_ids(cond_model_input).to(
cond_model_input_list = [cond_model_input[i].unsqueeze(0) for i in range(cond_model_input.shape[0])]
cond_model_input_ids = Flux2Pipeline._prepare_image_ids(cond_model_input_list).to(
device=cond_model_input.device
)
cond_model_input_ids = cond_model_input_ids.view(
cond_model_input.shape[0], -1, model_input_ids.shape[-1]
)

# Sample noise that we'll add to the latents
noise = torch.randn_like(model_input)
Expand All @@ -1650,6 +1654,8 @@ def get_sigmas(timesteps, n_dim=4, dtype=torch.float32):
packed_noisy_model_input = Flux2Pipeline._pack_latents(noisy_model_input)
packed_cond_model_input = Flux2Pipeline._pack_latents(cond_model_input)

noisy_len = packed_noisy_model_input.shape[1]

# concatenate the model inputs with the cond inputs
packed_noisy_model_input = torch.cat([packed_noisy_model_input, packed_cond_model_input], dim=1)
model_input_ids = torch.cat([model_input_ids, cond_model_input_ids], dim=1)
Expand All @@ -1668,7 +1674,8 @@ def get_sigmas(timesteps, n_dim=4, dtype=torch.float32):
img_ids=model_input_ids, # B, image_seq_len, 4
return_dict=False,
)[0]
model_pred = model_pred[:, : packed_noisy_model_input.size(1) :]
model_pred = model_pred[:, :noisy_len:]
model_input_ids = model_input_ids[:, :noisy_len:]

model_pred = Flux2Pipeline._unpack_latents_with_ids(model_pred, model_input_ids)

Expand Down